Architecture and integrations

Understand and design agents, RAG, memory, orchestration, APIs, MCP, and tool integrations, including their control and security boundaries.

Start here

Begin with these resources. The sections below organize the rest of the topic by subject.

Components and capabilities

How LLMs, retrieval, agents, and MCP divide the work, and where a system still falls short of the user's goal.

Memory, context, and retrieval

What an agent stores, what reaches the model on each call, and how to control which sources influence an answer.

Tools and orchestration

Who decides the next tool call, how controller loops and agent handoffs work, and what connected apps are allowed to do.

Security boundaries in integrations

Threat-model the integration layer, request assembly, permissions, and web retrieval, and protect private data in agent workflows.

Review a design or implementation

Check an implementation against official documentation and standards, with Skills and policies for architecture and implementation reviews.

Explore all topics